mlsanityData to 7 Oct 2026

Improving Variational Inference with Inverse Autoregressive Flow

arXiv 1606.04934 ↗First posted 15 Jun 2016cs.LG stat.MLcited by 636

Not on the map. Why?

Cited by 39 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The framework of normalizing flows provides a general strategy for flexible variational inference of posteriors over latent variables. We propose a new type of normalizing flow, inverse autoregressive flow (IAF), that, in contrast to earlier published flows, scales well to high-dimensional latent spaces. The proposed flow consists of a chain of invertible transformations, where each transformation is based on an autoregressive neural network. In experiments, we show that IAF significantly improves upon diagonal Gaussian approximate posteriors. In addition, we demonstrate that a novel type of variational autoencoder, coupled with IAF, is competitive with neural autoregressive models in terms of attained log-likelihood on natural images, while allowing significantly faster synthesis.

Key facts. Cited by 636 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Jun 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 161; 2022: 134; 2023: 106; 2024: 88; 2025: 87; 2026: 60.

636 papers.

Sort:

By area:

  1. 2023Mastering Diverse Domains through World Modelscited by 1,193
  2. 2021Variational Diffusion Modelscited by 1,145
  3. 2021VideoGPT: Video Generation using VQ-VAE and Transformerscited by 651
  4. 2021Score-based Generative Modeling in Latent Spacecited by 634
  5. 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 566
  6. 2021GAN Inversion: A Surveycited by 366
  7. 2022Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioningcited by 362
  8. 2022Understanding Diffusion Models: A Unified Perspectivecited by 337
  9. 2021How to Train Your Energy-Based Modelscited by 271
  10. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 251
  11. 2021D'ya like DAGs? A Survey on Structure Learning and Causal Discoverycited by 209
  12. 2021A Survey on Neural Speech Synthesiscited by 182
38 more
  1. 2022Offline Reinforcement Learning via High-Fidelity Generative Behavior Modelingcited by 177
  2. 2021Probabilistic Modeling for Human Mesh Recoverycited by 152
  3. 2022NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Qualitycited by 151
  4. 2022Concrete Score Matching: Generalized Score Matching for Discrete Datacited by 144
  5. 2024CycleResearcher: Improving Automated Research via Automated Reviewcited by 142
  6. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  7. 2022Flow Annealed Importance Sampling Bootstrapcited by 124
  8. 2021Fully Convolutional Cross-Scale-Flows for Image-based Defect Detectioncited by 117
  9. 2021An Introduction to Deep Generative Modelingcited by 104
  10. 2022DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latentscited by 103
  11. 2021Priors in Bayesian Deep Learning: A Reviewcited by 101
  12. 2021Neural Flows: Efficient Alternative to Neural ODEscited by 99
  13. 2021D2C: Diffusion-Denoising Models for Few-shot Conditional Generationcited by 96
  14. 2022Deep End-to-end Causal Inferencecited by 93
  15. 2021Annealed Flow Transport Monte Carlocited by 90
  16. 2023Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglementcited by 89
  17. 2024Normalizing Flows are Capable Generative Modelscited by 89
  18. 2021Variational Transformer Networks for Layout Generationcited by 88
  19. 2021Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flowscited by 84
  20. 2023GIVT: Generative Infinite-Vocabulary Transformerscited by 80
  21. 2021SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Datacited by 78
  22. 2021WaveFake: A Data Set to Facilitate Audio Deepfake Detectioncited by 78
  23. 2022An Introduction to Neural Data Compressioncited by 78
  24. 2021Real-time gravitational-wave science with neural posterior estimationcited by 76
  25. 2021Flow-based Kernel Prior with Application to Blind Super-Resolutioncited by 74
  26. 2021Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescalingcited by 73
  27. 2021Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codescited by 71
  28. 2021Generating Smooth Pose Sequences for Diverse Human Motion Predictioncited by 66
  29. 2022Continual Repeated Annealed Flow Transport Monte Carlocited by 66
  30. 2023Learning to Model the World with Languagecited by 66
  31. 2021High Fidelity Visualization of What Your Self-Supervised Representation Knows Aboutcited by 64
  32. 2022MUSE-VAE: Multi-Scale VAE for Environment-Aware Long Term Trajectory Predictioncited by 59
  33. 2021Hierarchical VAEs Know What They Don't Knowcited by 58
  34. 2022Your ViT is Secretly a Hybrid Discriminative-Generative Diffusion Modelcited by 58
  35. 2023Posterior Collapse and Latent Variable Non-identifiabilitycited by 57
  36. 2024Beyond ELBOs: A Large-Scale Evaluation of Variational Methods for Samplingcited by 55
  37. 2023High Fidelity Image Counterfactuals with Probabilistic Causal Modelscited by 53
  38. 2022Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systemscited by 50

50 most cited of 636 All 636 (JSON)